🧑‍🔬 Xu Wang

🏛️ Affiliations

🎓Guizhou UniversityGuiyang · China2026 · 1 papercurrent🎓Shanghai Jiao Tong UniversityShanghai · China2026 · 1 papercurrent🎓Tsinghua UniversityBeijing · China2026 · 1 papercurrent🎓University of Science and Technology of ChinaHefei · China2026 · 1 papercurrent

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. A Survey on Evaluation of Large Language Models (2023 · 3,648 citations)
   Large language models now serve both research and everyday users, including people with high-stakes needs such as students and patients.
2. Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models (2025 · 11 citations)
   Long chain-of-thought reasoning, as in DeepSeek-R1, improves LLM performance on hard problems. Obtaining it usually requires distillation or post-training on expensive long-CoT data. The authors instead strengthen reasoning at inference time by steering residual activations, using only ordinary (vanilla) CoT.
3. Model Unlearning via Sparse Autoencoder Subspace Guided Projections (2025 · 8 citations)
   The paper addresses selective knowledge removal from LLMs, where hazardous or private information must be erased without hurting general ability.
4. Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models (2026 · 3 citations)
   Sparse autoencoders (SAEs) break LLM hidden states into a small number of interpretable directions. In practice, though, they have mostly been used to inspect and label features after the fact, not to build or fix models. The Qwen Team addresses this with Qwen-Scope, an openly released collection of SAEs trained on…
5. CAR: Empowering Agents with Dynamic Tool Synthesis and Global Trajectory Rectification (2026)
   Tool-using LLM agents built on ReAct or Plan-and-Solve assume a fixed toolset. When a needed tool is missing, they fall back on long chains of atomic API calls. These chains can hit limits such as rate caps, and the agents then retry blindly. The retries fill the context with error logs and lead to hallucinated or…
6. REG: Retrieval via Emotion Similarity for Guiding Empathetic Dialogue Generation (2026)
   Retrieval-augmented empathetic chatbots usually pick example dialogues by semantic closeness. They can therefore pull in exemplars whose emotional tone contradicts the user's situation, such as a gloomy rain story for a cheerful one, which pushes the generator toward unsuitable replies.
7. Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding (2026)
   In streaming video understanding, a Video-LLM sees footage frame by frame. In the proactive setting, it must also decide when it has seen enough to answer a question about events that may happen later. Earlier solutions take one of three routes. Some fine-tune on frame-level silence/response labels, which tend to be…

All works

10 works of theirs in our library, the most cited first; 7 with a page here, the others link their original until we summarise them.

1. A Survey on Evaluation of Large Language ModelsACM Transactions on Intelligent Systems and TechnologyYupeng Chang, Xu Wang, Jindong Wang, et al.2023 · 3,648 citations
2. Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language ModelsConference on Empirical Methods in Natural Language Processing (EMNLP)Zihao Li, Xu Wang, Yuzhe Yang, et al.2025 · 11 citations
3. Model Unlearning via Sparse Autoencoder Subspace Guided ProjectionsConference on Empirical Methods in Natural Language Processing (EMNLP)Xu Wang, Zihao Li, Benyou Wang, et al.2025 · 8 citations
4. Qwen-Scope: Turning Sparse Features into Development Tools for Large Language ModelsarXiv:2605.11887Boyi Deng, Xu Wang, Yaoning Wang, et al.2026 · 3 citations
5. CAR: Empowering Agents with Dynamic Tool Synthesis and Global Trajectory RectificationFindings of the Association for Computational LinguisticsKai Wang, Xu Wang, Zhiyuan Fu, et al.2026
6. REG: Retrieval via Emotion Similarity for Guiding Empathetic Dialogue GenerationAnnual Meeting of the Association for Computational Linguistics (ACL)Xu Wang, Bo Wang, Yang Xiang, et al.2026
7. Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video UnderstandingAnnual Meeting of the Association for Computational Linguistics (ACL)Ke Ma, Jiaqi Tang, Bin Guo, et al.2026
8. UniCM: A Unified Consistency Model For Efficient Multimodal Generation and Understanding ↗Findings of the Association for Computational Linguistics: ACL 2026 · no summary yetChenkai Xu et al.2026
9. DMSD: Dual-Modal Semantic Disentanglement for Compositional Zero-Shot Learning ↗Findings of the Association for Computational Linguistics: ACL 2026 · no summary yetPan Yang et al.2026
10. ImpRIF: Stronger Implicit Reasoning Leads to Better Complex Instruction Following ↗Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetYuancheng Yang et al.2026

🤝 Co-authors here

12 of 28 co-authors with a page, the most papers together first.

• Zihao Li ×2
• Baosong Yang
• Benyou Wang
• Bo Wang
• Boyi Deng
• Cunxiang Wang
• Hao Chen
• Haoran Wei
• Huan Lin
• Jialong Tang
• Jiaqi Tang
• Jindong Wang

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Annual Meeting of the Association for Computational Linguistics (ACL) ×3: ACL 2026 ×2
• Conference on Empirical Methods in Natural Language Processing (EMNLP) ×2: EMNLP 2025 ×2
• Findings of the Association for Computational Linguistics: ACL 2026 ×2
• ACM Transactions on Intelligent Systems and Technology: ACM Transactions on Intelligent Systems and Technology 2023
• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026

🔗 Cited by

Papers of our library cite their works 665 times (of the 149,439 papers whose bibliographies we read); 143 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/xu-wang/